Gemini 3.1 Pro Preview
Google
Score
57
Rankings
Visuele pols van prestatieleiders die AnyInt aandrijven.
Filter benchmarks over intelligentie, snelheid, latentie, kosten, context en enterprise-gereedheid om de juiste intelligentie in uw AI-workflows te implementeren.
Models tracked30
Providers18
Top intelligence57
Fastest output301 tok/s
Intelligence
Intelligentie-indexrankings
AnyInt Intelligence Index v4.0 combineert 10 evaluaties waaronder redeneren, kennis, wiskunde- en coderingsbenchmarks. Hogere scores duiden op betere algehele intelligentie.
GPT-5.3 Codex (xhigh)
OpenAI
Score
54
Claude Opus 4.6 (max)
Anthropic
Score
53
Claude Sonnet 4.6 (max)
Anthropic
Score
52
GPT-5.2 (xhigh)
OpenAI
Score
51
GLM-5
Z AI
Score
50
GPT-5.2 Codex (xhigh)
OpenAI
Score
49
Kimi K2.5
Kimi
Score
47
Claude Opus 4.6
Anthropic
Score
46
Gemini 3 Flash
Google
Score
46
Qwen3.5 397B A17B
Alibaba
Score
45
MiniMax-M2.5
MiniMax
Score
42
DeepSeek V3.2
DeepSeek
Score
42
Grok 4
xAI
Score
42
MiMo-V2-Flash (Feb 2026)
Xiaomi
Score
41
Grok 4.1 Fast
xAI
Score
39
Claude Haiku 4.5
Anthropic
Score
37
KAT-Coder-Pro V1
KwaiKAT
Score
36
Nova 2.0 Pro (medium)
AWS
Score
36
gpt-oss-120B (high)
OpenAI(?)
Score
33
K-EXAONE
LG AI Research
Score
32
gpt-oss-20B (high)
OpenAI(?)
Score
24
NVIDIA Nemotron Nano 3
NVIDIA
Score
24
K2 Think V2
Kimi(?)
Score
24
Mistral Large 3
Mistral
Score
23
Llama 4 Maverick
Meta
Score
18
Context
Contextvensterrankings
De grootte van het contextvenster bepaalt hoeveel tekst het model in één verzoek kan verwerken. Grotere contextvensters maken analyse van langere documenten en complexere gesprekken mogelijk.
Grok 4.1 Fast
xAI
Window
2M
Llama 4 Maverick
Meta
Window
1M
Gemini 3.1 Pro Preview
Google
Window
1M
NVIDIA Nemotron Nano 4
NVIDIA
Window
1M
Gemini 3
Google
Window
1M
GPT-5.3 (xhigh)
OpenAI
Window
1M
GPT-5.2 Codex (xhigh)
OpenAI
Window
1M
K2 Think V2
Kimi
Window
400K
Qwen3.5 397B A17B
Alibaba
Window
400K
Mistral Large 3
Mistral
Window
400K
Grok 4
xAI
Window
262K
Nova 2.0 Pro (medium)
AWS
Window
256K
gpt-oss-120B (high)
OpenAI
Window
256K
Kimi K2.5
Kimi
Window
256K
K-EXAONE
LG AI Research
Window
256K
gpt-oss-20B (high)
OpenAI
Window
256K
MiMo-V2-Flash (Feb 2026)
Xiaomi
Window
256K
KAT-Coder-Pro V1
KwaiKAT
Window
256K
MiniMax-M2.5
MiniMax
Window
205K
Claude Opus 4.6 (max)
Anthropic
Window
200K
Claude Opus 4.6
Anthropic
Window
200K
Claude Sonnet 4.6 (max)
Anthropic
Window
200K
Claude Haiku 4.5
Anthropic
Window
200K
GLM-5
Z AI
Window
131K
DeepSeek V3.2
DeepSeek
Window
128K
Performance
Uitvoersnelheidsrankings
Uitvoersnelheid meet hoe snel het model tokens genereert. Hogere snelheden maken meer responsieve interacties en snellere voltooiing van lange inhoud mogelijk.
gpt-oss-120B (high)
OpenAI
Speed
301 tok/s
gpt-oss-20B (high)
OpenAI
Speed
299 tok/s
Grok 4.1 Fast
xAI
Speed
239 tok/s
Gemini 3 Flash
Google
Speed
213 tok/s
MiMo-V2-Flash (Feb 2026)
Xiaomi
Speed
158 tok/s
NVIDIA Nemotron Nano 3
NVIDIA
Speed
154 tok/s
Nova 2.0 Pro (medium)
AWS
Speed
132 tok/s
Claude Haiku 4.5
Anthropic
Speed
124 tok/s
Llama 4 Maverick
Meta
Speed
113 tok/s
GPT-5.3 Codex (xhigh)
OpenAI
Speed
98 tok/s
GPT-5.2 (xhigh)
OpenAI
Speed
91 tok/s
Gemini 3.1 Pro Preview
Google
Speed
88 tok/s
GPT-5.2 Codex (xhigh)
OpenAI
Speed
87 tok/s
Qwen3.5 397B A17B
Alibaba
Speed
81 tok/s
Claude Opus 4.6 (max)
Anthropic
Speed
72 tok/s
Claude 4.6
Anthropic
Speed
69 tok/s
Claude Opus 4.6
Anthropic
Speed
68 tok/s
GLM-5
Z AI
Speed
57 tok/s
KAT-Coder-Pro V1
KwaiKAT
Speed
56 tok/s
Claude Sonnet 4.6 (max)
Anthropic
Speed
54 tok/s
MiniMax-M2.5
MiniMax
Speed
50 tok/s
Mistral Large 3
Mistral
Speed
46 tok/s
DeepSeek V3.2
DeepSeek
Speed
42 tok/s
Kimi K2.5
Kimi
Speed
41 tok/s
Grok 4
xAI
Speed
41 tok/s